Google on Wednesday added a new agentive feature to Gemini. This feature, called Deep Research, was introduced with the new Gemini 2.0 family of AI models. It can create multi-step research plans, run web searches, and produce detailed reports on complex topics. The Mountain View-based tech giant says that the feature can be useful for researchers and students who have to write research papers. The new artificial intelligence (AI) feature is available on the web version of the chatbot for Gemini Advanced customers.
Gemini gets new deep research feature
Advanced reasoning has become a topic of interest for AI firms that are trying to increase the intelligence and processing power of their AI models. Advancing the analytical capability of large language models (LLMs) will require reimagining network architectures and learning algorithms, and researchers have developed some shortcuts to achieve this to some extent.
A popular method, used by OpenAI’s O1 model and a recently released model by Alibaba, increases computation time, allowing the AI to spend more time on a single question. This allows the AI to verify its answers, consider other options, and ultimately generate more detailed responses. Another way to do this is through AI agents, which is what Google did with the Gemini AI model.
Deep Research feature is basically an agentic feature. Once a user adds a question about a complex topic, the AI agent begins creating a multi-step research plan. A typical plan involves steps like breaking the topic into smaller parts, finding relevant research papers and articles on the topic, looking at trends, future impacts, and related areas.
Gemini Deep Research Agent Facility
Photo Credit: Google
Once the research plan is ready, users can intervene and add or remove steps or change them to better target the topic. After that the AI starts executing the plan and starts researching all the information. The agentic feature can also run multiple new web searches based on its learnings to understand additional topics.
After that, it analyzes the collected data, generates a detailed report and shows the output to the user. These reactions will usually be more intense and detailed than Gemini’s normal reaction. Google says this marketplace is ideal for researchers, academics, research students and even entrepreneurs.
Currently, Deep Research is available on the web version of the chatbot in Gemini Advanced in English language. Google highlighted that the feature will be made available in mobile apps as early as 2025. Deep Research can be found in the model selector drop-down menu and is listed as “Gemini 1.5 Pro with Deep Research”.
